This paper presents our preliminary experimental results on the encountered many problems when producing urban true orthoimages of downtown, where a number of high buildings prese...
Guoqing Zhou, Zhihao Qin, Susan Benjamin, J. Rand,...
Embedding algorithms search for low dimensional structure in complex data, but most algorithms only handle objects of a single type for which pairwise distances are specified. Thi...
Amir Globerson, Gal Chechik, Fernando C. Pereira, ...
We describe an algorithm for automatically learning discriminative components of objects with SVM classifiers. It is based on growing image parts by minimizing theoretical bounds ...
Bernd Heisele, Thomas Serre, Massimiliano Pontil, ...
While advances have been made in structuring, indexing and retrieval of multimedia documents, we propose to study the unexplored problematics of information retrieval on heterogen...
The aim of this work is to render high-quality views of a dynamic scene from novel viewpoints in real-time. An online system available at our institute computes the visual hull as...